Triple
T21629636
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | FirstRand Group |
E533794
|
entity |
| Predicate | tradedAs |
P2822
|
FINISHED |
| Object | JSE:FSR |
—
|
NE NERFINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: JSE:FSR | Statement: [FirstRand Group, tradedAs, JSE:FSR]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: JSE:FSR Context triple: [FirstRand Group, tradedAs, JSE:FSR]
-
A.
JSE
JSE is the youth wing of Spain’s Socialist Party, organizing and representing young people aligned with socialist and social-democratic ideals.
-
B.
JSE
chosen
JSE is the Johannesburg Stock Exchange, the primary securities exchange in South Africa and one of the largest in Africa.
-
C.
JSE:SAB
JSE:SAB was the Johannesburg Stock Exchange ticker symbol for SABMiller, one of the world’s largest multinational brewing and beverage companies before its acquisition by Anheuser-Busch InBev.
-
D.
JFS
JFS (Journaled File System) is a high-performance journaling file system developed by IBM, known for its scalability, low CPU usage, and reliability on enterprise and Linux systems.
-
E.
FSR
FSR is AMD's open-source spatial upscaling technology designed to boost gaming performance and image quality across a wide range of GPUs.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69e0c464fba881908d0ff2ac80511ce1 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69ef5215ae3c81909e6dedba23822970 |
completed | April 27, 2026, 12:09 p.m. |
Created at: April 16, 2026, 6:34 p.m.